© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 42041
    Prev
    Next
    INDEX
    Explanations

    force, force needed, force applied, force acting

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron is highly sensitive to mentions of mechanical force (e.g. “force,” “forces”) in technical contexts.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ,”
    -1.77
     ‚
    -1.59
    ’
    -1.55
     „
    -1.52
     ´
    -1.51
    的新
    -1.48
    ."
    -1.47
     ‘’
    -1.43
     według
    -1.41
     attaques
    -1.35
    POSITIVE LOGITS
    說的
    1.45
    悩む
    1.40
    леный
    1.35
     貓
    1.33
     portatil
    1.32
    eclamp
    1.31
    обои
    1.31
    følge
    1.30
    ів
    1.29
    ाइन
    1.28
    Activations Density 0.195%

    No Known Activations